Bradley Boswell
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bradley Boswell has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Gokila Dorai
Augusta University
3 shared publications - Rajaganapathy
DFAIR Lab, Augusta, GA 30912, USA
2 shared publications - Seth Barrett
School of Computer and Cyber Sciences, Augusta University, Augusta, GA 30912, USA
2 shared publications - Ahmed Aleroud
Augusta University
1 shared publication - Andrew A. Allen
Georgia Southern University
1 shared publication - Andrew Sanders
Computer and Cyber Sciences, Augusta University, Augusta, GA, USA
1 shared publication
Latest Publications
- 24 July 2026
- Published by Springer Nature
- p. 156-185
Adaptive Randomized Smoothing with Certified Robustness for Mitigating Tabular Adversarial Attacks
- 24 July 2026
- Published by Springer Nature
- p. 156-185
Adaptive Randomized Smoothing with Certified Robustness for Mitigating Tabular Adversarial Attacks
- 24 April 2026
- Published by Springer Nature
- p. 486-509
FLARE: Feature-Based Lightweight Aggregation for Robust Evaluation of IoT Intrusion Detection
- 24 April 2026
- Published by Springer Nature
- p. 486-509
FLARE: Feature-Based Lightweight Aggregation for Robust Evaluation of IoT Intrusion Detection
- 29 October 2025
- Published by Springer Nature
- p. 209-226
FIRE: Fog-Based Intrusion Detection Framework for Real-Time Security in IoT Environments
- 29 October 2025
- Published by Springer Nature
- p. 209-226
FIRE: Fog-Based Intrusion Detection Framework for Real-Time Security in IoT Environments
- Open Access
- 1 January 2024
- Published by HICSS Conference Office
Utilizing Convolutional Neural Networks and Eye-Tracking Data for Classroom Attention Tracking
Instructors often use facial cues of their students as key indicators of student attention levels. However, this method can pose a problem in online and computer-based learning environments. While other research has shown computer vision and eye-tracking could be used with machine learning techniques to predict attentiveness, they have shown only moderate success in terms of accuracy. In this work, we improve upon existing techniques for student attention tracking. We employed our previously developed Non-Intrusive Classroom Attention Tracking System (NiCATS) to collect facial images and eye-tracking data of students during three controlled experiments that represent common academic scenarios. Our first contribution is using convolutional neural networks to predict student attentiveness with an F1-Score of 0.91. Our second contribution is the validation of using eye-tracking metrics in conjunction with machine learning models to predict the attentiveness of students with up to 0.78 F1-Score, which could be useful when webcam privacy is a concern.
- 1 January 2024
- Published by HICSS Conference Office
Open AccessUtilizing Convolutional Neural Networks and Eye-Tracking Data for Classroom Attention Tracking
Instructors often use facial cues of their students as key indicators of student attention levels. However, this method can pose a problem in online and computer-based learning environments. While other research has shown computer vision and eye-tracking could be used with machine learning techniques to predict attentiveness, they have shown only moderate success in terms of accuracy. In this work, we improve upon existing techniques for student attention tracking. We employed our previously developed Non-Intrusive Classroom Attention Tracking System (NiCATS) to collect facial images and eye-tracking data of students during three controlled experiments that represent common academic scenarios. Our first contribution is using convolutional neural networks to predict student attentiveness with an F1-Score of 0.91. Our second contribution is the validation of using eye-tracking metrics in conjunction with machine learning models to predict the attentiveness of students with up to 0.78 F1-Score, which could be useful when webcam privacy is a concern.